Predicting catchment flow in a semi‐arid region via an artificial neural network technique

Abstract

Abstract:A model of rainfall-runoff relationships is an essential tool in the process of evaluation of water resources projects. In this paper, we applied an artificial neural network (ANN) based model for flow prediction using the data for a catchment in a semi-arid region in Morocco. Use of this method for non-linear modelling has been demonstrated in several scientific fields such as biology, geology, chemistry and physics.The performance of the developed neural network-based model was compared against multiple linear regressionbased model using the same observed data. It was found that the neural network model consistently gives superior predictions. Based on the results of this study, artificial neural network modelling appears to be a promising technique for the prediction of flow for catchments in semi-arid regions. Accordingly, the neural network method can be applied to various hydrological systems where other models may be inappropriate.

HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts

“…RMSE can provide a good measure of model performance for high flows (Karunanithi et al, 1994), but significant variations in the assessment of different catchments will occur, since the evaluation metric is dependent on the scale of the dataset that is being analysed. It is perhaps better to report RMSE, rather than Mean Squared Error (MSE; Chang et al, 2004;Chen et al, 2006;Furundzic, 1998;Riad et al, 2004;), because RMSE is measured in the same units as the original data, rather than in squared units, and is thus more representative of the size of a "typical" error. MSE was at one point the most widely used measure of overall accuracy for a forecasting method but it is also the method that has incurred the most criticism (e.g.…”

Neural network modelling of non-linear hydrological relationships

“…Neural technologies continue to make enormous strides in their struggle to become established as recognized tools that offer efficient and effective solutions for modelling and analysing the behaviour of complex dynamical systems. Time series forecasting has been a particular focus of interest and superior performing models have been reported in a diverse set of fields that include rainfall-runoff modelling (ASCE, 2000a, b;Dawson and Wilby, 2001;Birikundavy et al, 2002;Campolo et al, 2003;Huang et al, 2004;Riad et al, 2004;Hettiarachchi et al, 2005;Senthil Kumar et al, 2005) and sediment prediction (Abrahart and White, 2001;Nagy et al, 2002;Yitian and Gu, 2003;Kisi, 2004;Bhattacharya et al, 2005;Kisi, 2005). Moreover, for flood forecasting purposes, neural solutions offer practical advantages related to operational costs and socio-economic resources that would be of interest in developing countries, e.g.…”

An Assessment of a Proposed Hybrid Neural Network for Daily Flow Prediction in Arid Climate

“…The input vector was represented by rainfall (PCP) and runoff ( ) values for the previous five days. The reason that a five-day lag was chosen was due to the existence of rainfall events in five previous days (i.e., −1, −2, − 3, − 4, and − 5) [28]. The FF-MNN model can also be showed in the following compact format:…”

“…The transfer function is a required component for every process element (neuron) because the generating of output vectors in a neuron is related to the transfer function types [27]. In rainfall-runoff modeling, the sigmoid and linear transfer functions are the most popular functions, as mentioned in [28]. Table 1 indicates the applied transfer functions for this research.…”